The private AI appliance
An assembled, configured appliance that runs your AI assistant at home or in your office — small models on the device for everyday private work, and Claude, GPT, or Gemini through your own accounts when a task calls for more.
Local-first · Optional Life Upload · U.S.-based configuration and support
Edge — $1,699 · Edge Plus — $2,699 · One-time · No required subscription
Sound familiar?
Email, follow-ups, drafts, repetitive tasks. It keeps piling up while you're busy running the business.
We help you choose, set up, and optimize your AI solution with expert guidance and support.
Your data shouldn't live on someone else's server, and your assistant shouldn't disappear the moment a subscription lapses.
Personal
From $1,699
For one owner, everyday work, and private memory.
Professional
$6,999
For executives, developers, and serious professional use.
Organization
From $14,999
For larger models, multiple workloads, and private team infrastructure.
Cloud-only AI means renting month after month and sending your work to someone else's servers. Local-only AI means giving up the most capable models. Digital Twin Pro gives you both: private models on hardware you own, plus Claude, GPT, or Gemini through your own account whenever you want them.
Your 3-step path
Plug it in. Start delegating. Then give it your history.
Step 1: Plug In Your AI System
No display, keyboard, or mouse. Plug it in, finish the guided setup from your phone, and give your agent a name — anything you like.
Step 2: Start Delegating
Hand off the busywork — email, drafts, research, reminders — and watch it come back done. Everyday and sensitive work stays on the device; for the heaviest thinking, Hermes can call Claude, GPT, or Gemini through your own account.
Step 3: Give It Your History — Optional
With a one-time Life Upload, we load your approved archive — documents, notes, years of records — so your assistant answers like it was there all along. Get an instant estimate →
What's inside
Small, powerful models — like Google's Gemma — run right on the device, even offline. When a task deserves a frontier model, Hermes hands it to Claude, GPT, or Gemini — your account, your choice.
Tool-free cooling enclosure with integrated OLED status monitor
A full terabyte of fast built-in storage, pre-loaded and ready — nothing to configure.
Wi-Fi or Ethernet — pair from your phone, no monitor or command line.
Optionally personalized before shipment through guided onboarding and archive import.
No fine print: here is exactly where each kind of work happens, and what is transmitted when you choose to use an outside service.
| Mode | Where it runs | What leaves your device |
|---|---|---|
| Local models | Your system | Nothing is sent to a model provider |
| Local document search | Your system | Nothing is sent to a model provider |
| Claude, GPT, or Gemini (your account) | That provider | The selected prompt and any attached context, under the provider's terms |
| Telegram or WhatsApp | Messaging provider | Messages routed through that provider |
| Owner-authorized remote support | Approved secure channel | Only the system data required for the approved scope |
| Life Upload | Written project scope | Only the archive material you authorize, erased after import |
Full detail, including remote-access authorization and revocation: Security & Privacy
You decide, task by task. Everyday and sensitive work runs on the appliance in your home, stays there, and works even with no internet at all. When you choose to send a task to a cloud model like Claude or GPT, that request goes to the provider under your own account — and nothing else does.
Setup is guided from your phone. It arrives assembled and configured — no flashing, no monitor, no keyboard, no command line. Optional features like cloud models or messaging integrations require connecting your own accounts.
It's a capable personal AI assistant: answer questions, draft and summarize, organize your day, and run workflows you explicitly enable — with approved preferences and project context retained. It thinks on the device for everyday work and can call Claude, GPT, or Gemini through your account for the heaviest tasks. You can reach it from your phone or laptop.
Both kinds — that's the point. On the device, Hermes runs small, powerful open models, like Google's Gemma, that handle everyday work and keep private things private, even with no internet. When you want the most capable AI available, connect Claude, GPT, or Gemini with your own account, and Hermes hands the heavy thinking to them. You choose which brain gets which job.
You're buying the whole thing once — hardware, storage, and a private AI configured for you: $1,699 for Edge, or $2,699 for Edge Plus — larger local models, larger document collections, heavier multitasking, and more headroom for the years ahead; recommended for professionals. There's no required monthly fee because the assistant runs on hardware you own. Optional one-time services — like Life Upload, which loads your approved archive — are available whenever you want them.
You may request a return within 15 days of delivery; evaluation use is allowed. Return acceptance, return shipping, and any applicable restocking fee follow the Refund Policy.
Digital Twin Pro is built on NVIDIA Jetson — the family of small, efficient AI computers that powers robots, factory lines, and medical devices. Unlike an ordinary mini PC, a Jetson pairs its processor with a dedicated NVIDIA AI engine that shares one pool of memory, so it can run modern AI models around the clock while drawing about as much power as a light bulb. Silent, always on, and sized for a shelf — that's what lets Hermes live in your home instead of a datacenter. Each unit is assembled, configured, and supported in Miami, FL, USA.
One payment — $1,699 for Edge or $2,699 for Edge Plus — or buy today and pay over time with Shop Pay Installments: available options and terms are shown to eligible buyers at checkout. No required subscription, no surprise renewals. You may request a return within 15 days of delivery; evaluation use is permitted. Return acceptance, return shipping, and any applicable restocking fee follow the Refund Policy.
